StackHawk Wingman Gives Coding Agents a Security Partner
Techstrong TV Interviews
•
20m
Security testing for coding agents is where AppSec must go when AI writes most of the code. Scott Gerlach, co-founder and CSO of StackHawk, joins Alan Shimel on Techstrong TV. Furthermore, he explains why fixing, not finding, is now the real constraint.
About Scott Gerlach
Scott ran security teams at GoDaddy for about 10 years. In addition, he was CSO at SendGrid right before Twilio bought the company. Consequently, he and CEO Joni Klippert launched StackHawk to put application security inside development.
Why fixing matters more than finding
Frontier models have made finding vulnerabilities cheap for defenders and attackers alike. Meanwhile, AI generated code has blown past tickets waiting at the end of a queue. Therefore, remediation must become a core part of every step of software delivery.
Scott notes that open weight models give threat actors the same power with fewer safeguards. Furthermore, human reviewers cannot keep up with thousands of lines of generated code. As a result, security testing for coding agents has to run at AI scale.
Inside StackHawk Wingman
Wingman adds a deterministic security partner to your coding agent. In addition, it works like linters and unit tests, acting as a gate before code moves forward. Consequently, vulnerabilities go straight back into the agent loop to be fixed.
It ships as a single binary plus agent skills that teach any plugin capable agent to use StackHawk. Meanwhile, it runs in the IDE, on the command line or inside a software factory. Therefore, security testing for coding agents fits every stage of agentic maturity.
Results and availability
Since a June soft launch, Wingman has fixed more than 10,000 vulnerabilities. Furthermore, it is generally available with a 14 day free trial and then 10 dollars per user per month.
Explore more DevSecOps coverage and the latest Techstrong TV interviews.
For more information please visit stackhawk.com
Up Next in Techstrong TV Interviews
-
Why AI Agents Need Execution Governan...
Execution governance for AI agents is the next frontier of identity security. Roland Palmer, CISO and VP of IT at JumpCloud, joins Alan Shimel on Techstrong TV. Furthermore, he explains why checking a login is no longer enough once agents are inside.
About Roland Palmer
Roland spent 20 year...
-
AI Code Security Demands More Than an...
More Code, More Pressure on Security
AI code security is becoming a boardroom concern, not just a developer task. Coding assistants are accelerating software production. Meanwhile, attackers can use powerful models to discover weaknesses and develop exploits.Checkmarx CEO Sandeep Johri examines...
-
Inside Atlassian's Governed Agent Loo...
Governed agent loops are Atlassian's answer to scaling AI across the software lifecycle. Ming Wu, head of engineering for Dev AI at Atlassian, joins Alan Shimel on Techstrong TV. Furthermore, she explains how Jira becomes the control plane for agents.
About Ming Wu
Ming earned her PhD at Mi...